Category: Data Source
The Real Significance of Changes in the Gender Happiness Gap
A qualifier: None of these comparisons are entirely satisfactory. For instance, if you believe that there is very little variation in happiness across people, time, or states of the economy, then you would interpret the above comparisons as suggesting that the change in the female happiness gap is big, only when compared with small things.
Another qualifier: We only document changes in the measured gender happiness gap.
Any other ideas on how to describe the "oomph" (or economic significance) of changes in qualitative variables like happiness?
[Thanks to Betsey Stevenson for coauthoring this post.]
UPDATE 1: Steve Levitt chimes in.
UPDATE 2: Jezebel adds some perspective.
The Significance of Changes in the Gender Happiness Gap
- A
misunderstanding. I suspect that the
claim that happiness did not significantly change from 1972-2006 comes from the
fact that we did not include stars when reporting the implied gender gaps in Table
1 of our paper. Thus, the claim that
the ordered probit analysis found that the "Gender
happiness gap" was not statistically significant, either in 1972 or in
2006, even at the 0.10 level
is simply untrue. Here’s the relevant part of Table 1, which is
an ordered probit regression, of happiness on time trends by gender:
The right way to test for whether women
were, on average, happier at the start of the sample is to look at the “Female
dummy”, which is clearly significant. The right way to ask whether this gender gap has changed is to look at
the difference in trends, which is also clearly significant. The last two rows are regression-based predicted
values, so we didn’t think we should put stars next to these numbers.
- Statistical
mischief: When you want to make a result go away, throw away enough data,
and a result will become insignificant. For instance pooling all of the data gives us a useful 46,303
observations. Analyze any specific year,
and you are left with only 1,500-3,000 data points. Even so, let’s analyze only data from 1972
and 2006:- %Very happy = 28.7 + 3.1*Female +1.6*(Year2006)
– 2.4*(Female in 2006) - %Not too happy = 18.1 -3.2*Female – 5.5*(Year2006)
+ 4.1*(Female in 2006)
- %Very happy = 28.7 + 3.1*Female +1.6*(Year2006)
In the first case, no coefficients are
statistically significant, and in the latter, all are. In both cases, the estimates say that women
were once a fair bit happier than men, and this is no longer true. Comparing this regression with those in our
paper, we simply learn that a smaller sample yields similar estimates, but they
are less likely to be statistically significant.
- Looking for
a masterpiece, when we are doing collage. Sometimes studying social
phenomena is hard, and one draws on many data sources to put together a collage
of evidence. Our paper finds declining
happiness among women relative to men in: the General Social Survey (n=46,303
from 1972-2006); the Virginia Slims Poll (n=26,701 from 1972-2000); among U.S.
12th graders (Monitoring the Future; n=433,906 from 1976-2005); in the
United Kingdom (British Household Panel Study data from 1991-2004; n=121,135);
in Europe (the Eurobarometer analysis has n=636,400 from 1973-2002, covering 15
countries), and across developed countries (the International Social Survey
Program contains surveys 35 countries from 1991-2001 yielding n=97,462). The only dataset that does not yield clear
results of a decline in women’s happiness relative to men’s is the World Values
Survey, and even there, the data do not speak clearly.
Let me try to give a particularly transparent description of the data,
simply splitting the GSS data into two periods, 1972-1989 v. 1990-2006. There was a clear gender happiness gap in the
earlier period (34.3% of women were very happy v. 31.8% of men). This difference is clearly statistically
significant (t=4.1). In the later
period, 30.9% of women were very happy, compared with 31.1% of men. This recent gender happiness gap is
insignificant (t=-0.3). The decline in
the share of women who were very happy (34.3% v. 30.9%) is clearly significant
(t=5.9), while the corresponding changes for men were not (t=-1.1). The decline in the share of women who were
very happy relative to men is also significant (t=-3.1). Analyzing the share who are “not too happy”
yields a roughly similar pattern (but in reverse): an insignificant “unhappiness
gap” in the earlier period, but a significant gap emerged in the latter period. Interestingly, the “unhappiness gap” emerged
because as men became less likely to be unhappy, as women’s unhappiness
remained largely stable. The ordered
probit is a regression technique that allows one to make these happiness and
unhappiness comparisons all at the same time; these regressions tell us that
there was a gender happiness gap favoring women in the earlier period, and it
now favors men. For the
regression-heads, if your library subscribes can download the GSS data from the
ICPSR here. I’ll post some stata code in the comments.
This post only deals with whether the effects we
describe in
the paper are statistically significant. The other complaint is that
our results are too small to matter. Later today, I’ll turn to how we
think
about whether these are large or small effects.
[Written jointly with my coauthor Betsey Stevenson]
UPDATE: See discussion of "economic significance" here.
Intriguing numbers on conscientious objectors
The GAO reports only 425 applications for conscientious objector status from 2002-2006, compared with 2.3 million servicemembers (including Reserves). Just over half were approved. Read more here.
Hat Tip, Zubin Jelveh, who also notes:
For reference, the Vietnam war had about 200,000 such applications.
(Of course, Vietnam did have a draft.)
Facts and True Facts: More on Divorce
My
initial guest post noted that recent
divorce statistics were misinterpreted widely in both the media,
and by the academics interviewed by the press. The question is what went wrong with the latest data?
First, some necessary background. This
table was published by the Census Bureau counting the proportion of those
who had wed in each year who subsequently celebrated various
anniversaries. Here’s a quick test: Look
at the data, and decide for yourself what is happening to marital
stability. Or if you are lazier, let me
help with an example: the Census reported that 76.4% of men whose first wedding
occurred in 1985-89 had celebrated a tenth anniversary; this declined rather
dramatically to 70.0% among those who marrying in 1990-94. By jingo, it looks like recent marriages have
become much less stable!
Not so fast. The
marital history data were collected from July-September 2004, and hence those
who had married in, say, October 1994, simply
could not have reached their tenth anniversary by the survey date. Because this affected around one-in-ten of
those wed from 1990-94, this statistical factor alone explains what looked like
a decline in marital stability.
How do we interpret what happened?
- The
Census Bureau reported true and useful facts: The data are interesting, and
the table includes a small footnote, noting “Approximately 10 percent of the
cohort has not reached the stated age by the end of the latest specified time
period. Because of this, estimates for this group for the highest anniversary
are low.” With this qualification, one
should not conclude that divorce is rising. (But what should one conclude? No
guidance is given.) - The
Census Bureau reported true, but useless facts: The tables measure exactly
what it says it measures. The Census
Bureau is like Fox news:
We report, you decide. And we report,
even if the number we report is meaningless. - The Census
Bureau reported misleading facts: It is obvious that a qualifying footnote will
be ignored by most. Indeed, the New York
Times printed
the table but omitted the footnote. But
let’s not be too harsh on the NY Times: I talked about these data with several excellent
economists, and none even noticed the
footnote. Headline numbers deserve
headline qualifications. - The
survey was flawed: If the Census is interested in measuring the survival of
a set of marriages to their tenth anniversary, then failing to wait ten years after
a wedding to measure this is a surveying glitch.
So what is the mission of a statistical agency? If the Census’ job is to just report back
what we (the surveyed population) tell them, then they performed that task
adequately. If their job is to report
parameters – useful facts – then they failed miserably, as the data they
reported are hopeless biased indicators of marital stability. Alternatively, the question is: Does the
Census provide facts, or interpretation? I’m happy if they present only facts and leave the interpretation to experts. But is there an obligation to report only interpretable
facts?
Stephen Colbert’s term “truthiness“,
the reigning word of
the year, refers to what you
want the facts to be as opposed to what the facts are. I’m wondering, what is the right word is for something that is a fact but isn’t true? Untruthiness, anyone?
The Divorce Myth
I want to start my week guest blogging by talking about divorce. Betsey Stevenson and
I had an
op-ed in yesterday’s New York Times noting a very simple fact: those
married in the 1990s have proved less likely to divorce than those wed in the
1980s, which were less likely to divorce than those wed in the 1970s. The
Divorce Facts are that divorce is falling, and marriages are more stable.
What is surprising, is just how easily and how often the
Divorce Facts lose out to the Divorce Myth. The Divorce Myth is that divorce
is rising. When the latest
divorce numbers came out last week, they once again confirm this
quarter-century long decline in divorce, but the media (including the Times,
Post,
and the Inquirer)
chose instead to write (incorrectly) about rising divorce. (In their defense, the data were presented in
a way that invited misinterpretation, a subject that I shall return to in a
future post.)
Why the persistence of the Divorce Myth?
- Blame the
public for underestimating divorce: Tyler
has argued that Americans “underestimate the probability of divorce”, and
so when the statistics show that divorce is quite common, they infer divorce
must have risen. - Blame the
public for overestimating divorce: Greg
Mankiw thinks that this “seems be an example of what Bryan Caplan calls ‘the
pessimistic bias’, a tendency to overestimate the severity of economic problems.” - Blame the
press: Mankiw may be a bit unfair on Joe Citizen: the average person gets
their news from the press, and in this case, the press reported falsehoods as
facts. - Blame the
politics: We argued that “Reporting on our families is a lot like reporting
on the economy: statistical tales of woe provide the foundation for reform
proposals. The only difference is that
conservatives use these data to make the case for greater government
intervention in the marriage market, while liberals use them to promote
deregulation of marriage.” - Blame the
professors: Academics are meant to provide the facts offsetting the
political hacks. But we don’t. Economists have had too little respect for
simple facts; publication glory lies with grand theories. Ideologically-motivated profs teaching family
sociology or family law would rather reinforce the Myth than offset it.
Personally, I go for #4 causing #3, unchecked by #5, and
would love to see research by Bryan testing #1 v. #2. Your thoughts?
Heroes are not Replicable
You know the plot. Young, idealistic teacher goes to inner-city high school. Said idealistic teacher is shocked by students who don’t know the basics and who are too preoccupied with the burdens of violence, poverty and indifference to want to learn. But the hero perseveres and at great personal sacrifice wins over the students using innovative teaching methods and heart. The kids go on to win the state spelling/chess/mathematics championship. c.f. Stand and Deliver, Freedom Writers, Dangerous Minds etc.
We are supposed to be uplifted by these stories but they depress me. If it takes a hero to save an inner city school then there is no hope. Heroes are not replicable.
What we need to save inner-city schools, and poor schools everywhere, is a method that works when the teachers aren’t heroes. Even better if the method works when teachers are ordinary people, poorly paid and ill-motivated – i.e. the system we have today.
In Super Crunchers, Ian Ayres argues that just such a method exists. Overall, Super Crunchers is a light but entertaining account of how large amounts of data and cheap computing power are improving forecasting and decision making in social science, government and business. I enjoyed the book. Chapter 7, however, was a real highlight.
Ayres argues that large experimental studies have shown that the teaching method which works best is Direct Instruction (here and here are two non-academic discussions which summarizes much of the same academic evidence discussed in Ayres). In Direct Instruction the teacher follows a script, a carefully designed and evaluated script. As Ayres notes this is key:
DI is scalable. Its success isn’t contingent on the personality of some uber-teacher….You don’t need to be a genius to be an effective DI teacher. DI can be implemented in dozens upon dozens of classrooms with just ordinary teachers. You just need to be able to follow the script.
Contrary to what you might think, the data also show that DI does not impede creativity or self-esteem. The education establishment, however, hates DI because it is a threat to the power and prestige of teaching, they prefer the model of teacher as hero. As Ayres says "The education establishment is wedded to its pet theories regardless of what the evidence says." As a result they have fought it tooth and nail so that "Direct Instruction, the oldest and most validated program, has captured only a little more than 1 percent of the grade-school market."
The Straight Talk from Market Prices
According to the betting markets (at least intrade.com), Ron Paul has officially passed John McCain in terms of the probability of winning the Republican nomination. Amazing – however you read the tea leaves.
Thanks to Tim Groseclose for the pointer.
Sentences of provocation
Our results suggest that if all states had primary enforcement seatbelt laws then regular youth seatbelt use would be nearly universal and youth fatalities would fall by about 120 per year.
Here is the paper. My question: how many expected saved lives are required for this law to be a good idea? Any comment on this post should suggest a specific numerical answer to that question.
Facts about rich people
In the first Forbes 400 [1982], oil was the source of 22.8 percent of the fortunes, manufacturing 15.3 percent, finance 9 percent, and technology 3 percent. By 2006 oil had fallen to 8.5 percent and manufacturing to 8.5 percent. Technology, however, had risen to 11.75 percent and finance to an extraordinary 24.5 percent.
And get this:
The average net worth in 2006 of Forbes 400 members without a college degree was $5.96 billion; those with a degree averaged $3.14 billion. Four of the five richest Americans — Bill Gates, casino owner Sheldon Adelson, Oracle’s Larry Ellison, and Microsoft cofounder Paul Allen…– are college dropouts.
Both are from the quite engaging All the Money in the World — How the Forbes 400 Make — And Spend — Their Fortunes, by Peter W. Bernstein and Annalyn Swan.
In inflation-adjusted terms, here are the richest Americans of all time; Bill Gates is #13. Here are graphs on California vs. New York.
Suicide help lines
In 723 of 1,431 calls, for example, the helper never got around to asking whether the caller was feeling suicidal. And
when suicidal thoughts were identified, the helpers asked about
available means less than half the time. There were more egregious
lapses, too: in 72 cases a caller was actually put on hold until he or
she hung up. Seventy-six times the helper screamed at, or was rude to,
the caller. Four were told they might as well kill themselves.There were 33 evident on-line suicide attempts, yet only six rescue
efforts, sometimes because the caller ended the communication. In one
case, a caller who’d overdosed passed out, yet the helper hung up.
Here is the full story, by Christopher Shea. I am curious how much of this problem is due to the non-profit structure of the institutions running the lines and how much is due to the behavioral quirks of human beings faced with the suicidal tendencies of others…
From the comments: "Also, how would a for-profit suicide hotline work? Call a 900 number if
you’re having suicidal thoughts? I find it hard to imagine that a
for-profit suicide hotline system would generate *more* suicide
prevention, though maybe I’m wrong."
Prediction tools
Predict How Long You’ll Live (Northwest Mutual)
Predict Your Child’s Due Date (Ayres)
Predict Your Child’s Adult Height (University of
Saskatchewan)
Predict Justice Kennedy’s Vote (Ayres)
Predict Your Next Move in Rock-Paper-Scissors (Chappie)
There are many other prediction tools here (do click), from Ian Ayres. Ayres requests that you email him other prediction applets, which he will add to the page. Ayres also has a new book out, Super Crunchers: Why Thinking by Numbers is the New Way to be Smart; it is highly readable and also endorsed by Steve Levitt.
I thank Ian Ayres for the pointer.
Mobility
Here is the latest, by Emmanuel Saez and co-authors; note I linked to this paper yesterday but now I have looked at it. Here is one key sentence:
…we find that short-term and long-term mobility among all workers has been quite stable since the 1950s.
To disaggregate, note that mobility among males is down but mobility among females is up. (It is an interesting question whether there is a causal relationship here.)
Here is a much earlier MR post on mobility. Keep these links in mind next time you hear claims about mobility, and I believe you will hear many such claims in September. See also our earlier posts on Dalton Conley, who shows just how much inequality is generated within the same family.
It should be noted that Saez is the leading measurer of income inequality and also a critic of such inequality. In his view a constant level of mobility means that no force is offsetting ongoing inequality. I believe he would likely read his own paper as support for a left-wing view of the world and as support for concern with income inequality. He would not read his work as reason to dismiss the mobility issue. My view differs, as I worry about mobility — can a hard-working person get ahead? — but I do not worry about inequality per se, nor do I require of mobility that it overturn a particular level of inequality.
Assorted Links
- China has banned Buddhist monks in Tibet from reincarnating without government
permission.
- Craig Venter is one step closer to becoming a god.
- 500 Years of female faces in western art (video).
The J.K. Rowling effect
A YouGov poll has found that almost 10% of Britons aspire to being an
author, followed by sports personality, pilot, astronaut and event
organiser on the list of most coveted jobs.
Here is the link. Event organiser?
Department of Yikes
Overall, 74 percent [of men visiting streetwalkers] reported that they always wear a condom (men with stable relationships were less likely to use protection, at least with prostitutes).
It’s not so hard to write down the underlying utility function here, is it?
That is from the September 2007 issue of Atlantic Monthly, citing research by economist Marina della Giusta and others, published in Applied Economics. The working paper seems to be here.
In another development at Atlantic Monthly, but unrelated to the above factoid, or to the more general idea of yikes, the new Megan McArdle blog is now up and running. Here is Megan’s post on what old people deserve.